© 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. 19-RESID-POST-AA
    11. 102951
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    торы
    -0.09
     शुक्र
    -0.08
    _best
    -0.08
    환경
    -0.08
     Ariel
    -0.08
     Audience
    -0.08
    тор
    -0.08
     બદલ
    -0.08
    ią
    -0.08
     Aroma
    -0.08
    POSITIVE LOGITS
     endorsements
    0.09
     manuals
    0.08
    。不
    0.08
     compartilh
    0.08
     placas
    0.08
     pilers
    0.08
     compart
    0.08
    Qed
    0.08
     verdadeiro
    0.07
    shared
    0.07
    Activations Density 0.000%

    No Known Activations