© 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. 24767
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Carpet
    -0.08
     locations
    -0.08
    程度
    -0.08
    äk
    -0.08
    νει
    -0.08
     הדרך
    -0.07
     sleepers
    -0.07
     clinician
    -0.07
    fle
    -0.07
     rubble
    -0.07
    POSITIVE LOGITS
     minus
    0.10
     Minus
    0.10
    Minus
    0.08
    -minus
    0.08
     Vers
    0.08
    aylor
    0.07
     Gavin
    0.07
     ZX
    0.07
    .minus
    0.07
     Forms
    0.07
    Activations Density 0.043%

    No Known Activations