© 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. 108679
    Prev
    Next
    INDEX
    Explanations

    and

    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
    responses
    -0.08
    Cell
    -0.08
     punctual
    -0.08
     piled
    -0.08
    bringen
    -0.08
    adic
    -0.08
     생
    -0.08
    Healthy
    -0.08
    regional
    -0.08
    Comfort
    -0.07
    POSITIVE LOGITS
     manera
    0.08
     cuándo
    0.08
     vi
    0.08
     As
    0.08
     نست
    0.07
     xv
    0.07
     كيف
    0.07
     کیسے
    0.07
     کب
    0.07
     Pit
    0.07
    Activations Density 0.014%

    No Known Activations