© 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. 48241
    Prev
    Next
    INDEX
    Explanations

    emp

    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
    ieuse
    -0.08
    usual
    -0.08
    unes
    -0.08
    total
    -0.08
    644
    -0.08
    datepicker
    -0.07
    isex
    -0.07
    passes
    -0.07
    moment
    -0.07
    skyld
    -0.07
    POSITIVE LOGITS
    iri
    0.08
     thống
    0.08
     Roofing
    0.08
     Rugs
    0.08
    ilh
    0.08
     zomwe
    0.07
    irik
    0.07
    专题
    0.07
    聊天
    0.07
     berm
    0.07
    Activations Density 0.000%

    No Known Activations