© 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. 23-RESID-POST-AA
    11. 97453
    Prev
    Next
    INDEX
    Explanations

    .Default

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Opin
    -0.08
    bage
    -0.08
    Own
    -0.08
     opinion
    -0.07
    _string
    -0.07
     Pequ
    -0.07
    .ag
    -0.07
    agory
    -0.07
    -0.07
     Unternehmens
    -0.07
    POSITIVE LOGITS
     torsdag
    0.08
     proximal
    0.08
    headers
    0.08
    غر
    0.08
    цом
    0.08
    Headers
    0.08
    ิดต่อ
    0.07
    Request
    0.07
     قريب
    0.07
    екомен
    0.07
    Activations Density 0.001%
    No Known Activations