© 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. 11-RESID-POST-AA
    11. 75624
    Prev
    Next
    INDEX
    Explanations

    debugging and assertions

    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
     Vielfalt
    -0.08
     llegada
    -0.08
     chicas
    -0.08
     arrival
    -0.08
     urn
    -0.08
     fragmented
    -0.08
    办理
    -0.07
    >{"
    -0.07
    iú
    -0.07
    umna
    -0.07
    POSITIVE LOGITS
    DEBUG
    0.10
     DEBUG
    0.10
    .Debug
    0.09
    .debug
    0.09
    (debug
    0.09
    /debug
    0.09
     deaktiv
    0.09
    (DEBUG
    0.09
     debug
    0.08
    .DEBUG
    0.08
    Activations Density 0.004%

    No Known Activations