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. 49334
    Prev
    Next
    INDEX
    Explanations

    Serial

    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
     fab
    -0.08
     Lam
    -0.08
    Lam
    -0.07
     males
    -0.07
    rones
    -0.07
     babel
    -0.07
     cuidados
    -0.07
     vacant
    -0.07
     teeth
    -0.07
     ANG
    -0.07
    POSITIVE LOGITS
     buffer
    0.08
     Resist
    0.08
    805
    0.07
    797
    0.07
     subsystem
    0.07
     pad
    0.07
    .buffer
    0.07
    ('?
    0.07
    052
    0.07
     స
    0.07
    Activations Density 0.001%

    No Known Activations