© 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. 47213
    Prev
    Next
    INDEX
    Explanations

    AI agents

    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
     mn
    -0.08
    initializer
    -0.08
    Resistance
    -0.08
    ference
    -0.07
    clin
    -0.07
     jej
    -0.07
     Bournemouth
    -0.07
     Resistance
    -0.07
    adians
    -0.07
    /not
    -0.07
    POSITIVE LOGITS
     realizados
    0.08
     siguiendo
    0.08
    0.08
    ський
    0.07
     durchführen
    0.07
     gevolgd
    0.07
     Enero
    0.07
     spun
    0.07
     expressly
    0.07
     encar
    0.07
    Activations Density 0.000%

    No Known Activations