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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24822
    Prev
    Next
    INDEX
    Explanations

    Filler words/verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     electr
    -0.09
     刘
    -0.08
    _ITER
    -0.07
    ACION
    -0.07
    _REG
    -0.07
     Header
    -0.07
     갑
    -0.07
     Charging
    -0.07
     всему
    -0.07
     해당
    -0.07
    POSITIVE LOGITS
     hoki
    0.13
     hatta
    0.09
     też
    0.09
     എന്നിവ
    0.09
     तथा
    0.08
     संगठन
    0.08
     എന്നീ
    0.08
     وحتى
    0.08
     And
    0.08
     organisasi
    0.08
    Activations Density 0.812%

    No Known Activations