© 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. 95371
    Prev
    Next
    INDEX
    Explanations

    AST ALT

    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
     multim
    -0.08
    $url
    -0.08
     adh
    -0.08
    ,"
    -0.07
    стыр
    -0.07
    енным
    -0.07
    [href
    -0.07
    itarian
    -0.07
    ''''
    -0.07
    _gen
    -0.07
    POSITIVE LOGITS
    tempor
    0.08
     promptly
    0.08
     Bein
    0.08
    Immediate
    0.08
     errores
    0.08
     imediato
    0.08
     Snapshot
    0.08
     unmittel
    0.07
     nutrient
    0.07
     equiv
    0.07
    Activations Density 0.001%

    No Known Activations