© 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. 102807
    Prev
    Next
    INDEX
    Explanations

    FF

    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
    :
    -0.09
     bruis
    -0.08
    ,
    -0.08
     redness
    -0.08
     frowned
    -0.07
     Tint
    -0.07
    .P
    -0.07
    :J
    -0.07
    -0.07
     pytest
    -0.07
    POSITIVE LOGITS
    _STRUCTURE
    0.09
    \Framework
    0.09
     evitare
    0.09
    950
    0.08
    ალკ
    0.08
     concentrate
    0.08
    572
    0.08
    欧美日韩
    0.08
     ?");↵
    0.08
     علاوہ
    0.08
    Activations Density 0.000%
    No Known Activations