© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    control

    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
     చెందిన
    -0.08
    Attack
    -0.08
    Bew
    -0.08
     eater
    -0.08
     biochemical
    -0.08
    Cg
    -0.07
    Audit
    -0.07
     grassy
    -0.07
    .point
    -0.07
    Comput
    -0.07
    POSITIVE LOGITS
    措施
    0.09
     convivencia
    0.08
     estancia
    0.08
     Eugen
    0.08
    acola
    0.08
     contraception
    0.08
     הבית
    0.08
     قص
    0.08
     condoms
    0.08
     elección
    0.08
    Activations Density 0.009%

    No Known Activations