© 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. 23-RESID-POST-AA
    11. 97213
    Prev
    Next
    INDEX
    Explanations

    Arabic

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juurde
    -0.09
    eco
    -0.08
     volk
    -0.08
    ynt
    -0.08
    roh
    -0.07
     хий
    -0.07
    гэ
    -0.07
    ged
    -0.07
    בח
    -0.07
    ahlt
    -0.07
    POSITIVE LOGITS
     Bieber
    0.08
    猫
    0.07
     katten
    0.07
     recomendaciones
    0.07
     Cef
    0.07
     lossen
    0.07
     nung
    0.07
     което
    0.07
    冊
    0.07
    .breakpoints
    0.07
    Activations Density 0.000%

    No Known Activations