© 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. 3-RESID-POST-AA
    11. 12930
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simplify
    -0.09
     அது
    -0.08
     উত্ত
    -0.08
     самим
    -0.07
     திர
    -0.07
     리
    -0.07
     சிற
    -0.07
    efe
    -0.07
     ஒரு
    -0.07
     듣
    -0.07
    POSITIVE LOGITS
    cute
    0.08
     Va
    0.08
    @extends
    0.08
     bloss
    0.08
     Sau
    0.08
     jau
    0.08
    Whats
    0.07
    орган
    0.07
     Vien
    0.07
    ->{'
    0.07
    Activations Density 0.000%

    No Known Activations