Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90300
    Prev
    Next
    INDEX
    Explanations

    gravitational

    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
    avy
    -0.08
     Automotive
    -0.08
     представлены
    -0.08
     Outcome
    -0.08
    .decorators
    -0.08
     Presidency
    -0.08
     Rosen
    -0.08
     retiro
    -0.07
    elescope
    -0.07
     Segment
    -0.07
    POSITIVE LOGITS
     costs
    0.09
     खर्च
    0.08
     informace
    0.08
     jerk
    0.08
     সংঘ
    0.08
     koszt
    0.08
     비용
    0.08
    碰
    0.08
     ખર્ચ
    0.08
     alone
    0.08
    Activations Density 0.006%

    No Known Activations