© 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. 11-RESID-POST-AA
    11. 26402
    Prev
    Next
    INDEX
    Explanations

    requirement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alterations
    -0.08
     terlebih
    -0.08
     sap
    -0.08
     Carn
    -0.08
    priv
    -0.08
     تس
    -0.08
    becue
    -0.07
    sap
    -0.07
    prefer
    -0.07
     contudo
    -0.07
    POSITIVE LOGITS
    คือ
    0.11
     này
    0.09
    如下
    0.09
     Svens
    0.08
     disso
    0.08
     Thomson
    0.08
     Cheng
    0.08
     ഘ
    0.08
     suivants
    0.07
     ovan
    0.07
    Activations Density 0.116%

    No Known Activations