© 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. 7-RESID-POST-AA
    11. 1233
    Prev
    Next
    INDEX
    Explanations

    research, rating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ddl
    -0.09
     zure
    -0.08
     recount
    -0.08
     erm
    -0.08
     baut
    -0.08
     haver
    -0.08
     ceremony
    -0.08
     BDSM
    -0.08
    DDL
    -0.08
     toal
    -0.07
    POSITIVE LOGITS
     bearish
    0.11
     bullish
    0.11
     analyst
    0.10
     forecasts
    0.10
     overpriced
    0.09
     прогноз
    0.09
     predicting
    0.09
     Futures
    0.09
     mainstream
    0.08
     normals
    0.08
    Activations Density 0.034%

    No Known Activations