© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16487
    Prev
    Next
    INDEX
    Explanations

    say "ity" ending

    np_max-act-logits · gemini-2.0-flash

    the word fragments "ial" and "ity" that form the suffix of "bestiality" in policy violation discussions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @grunklewordner
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advance
    -0.08
    هما
    -0.08
    ,+
    -0.08
    Advance
    -0.08
    /+
    -0.07
    /max
    -0.07
    CBC
    -0.07
     (+
    -0.07
    (Module
    -0.07
     sayesinde
    -0.07
    POSITIVE LOGITS
     животных
    0.14
     animaux
    0.13
     Tiere
    0.13
    动物
    0.13
     animals
    0.12
     animal
    0.12
     الحيوانات
    0.12
    禽
    0.12
     zoon
    0.12
     animais
    0.12
    Activations Density 0.005%

    No Known Activations