© 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. 3-RESID-POST-AA
    11. 2576
    Prev
    Next
    INDEX
    Explanations

    –

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theros
    -0.08
     Philosoph
    -0.07
    arket
    -0.07
    ران
    -0.07
    liy
    -0.07
    outer
    -0.07
    hydrate
    -0.07
     прип
    -0.07
    -0.07
    expiration
    -0.07
    POSITIVE LOGITS
     Lund
    0.09
     coined
    0.08
    감
    0.08
     Rotten
    0.08
     embell
    0.08
     convicted
    0.07
     Amsterdam
    0.07
    純
    0.07
     dön
    0.07
    appar
    0.07
    Activations Density 0.036%
    No Known Activations