© 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. 102729
    Prev
    Next
    INDEX
    Explanations

    legal intellectual property contracts

    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
     orice
    -0.08
     nunca
    -0.08
     aldri
    -0.08
    itin
    -0.08
    -0.07
    .jsdelivr
    -0.07
    ení
    -0.07
     deeper
    -0.07
    ുര
    -0.07
     insufficient
    -0.07
    POSITIVE LOGITS
     conveniently
    0.09
     특정
    0.09
     zogenaamde
    0.08
    ৃথ
    0.08
     Convenient
    0.08
     netjes
    0.08
     lucr
    0.08
     것입니다
    0.08
     eyiti
    0.08
     작품
    0.08
    Activations Density 0.000%
    No Known Activations