© 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. 26361
    Prev
    Next
    INDEX
    Explanations

    outputs

    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
     verbose
    -0.08
     Afro
    -0.08
    oley
    -0.08
     operands
    -0.07
     ACS
    -0.07
     DT
    -0.07
    יאת
    -0.07
    慰
    -0.07
     Arturo
    -0.07
     Beim
    -0.07
    POSITIVE LOGITS
     col
    0.08
     fecha
    0.08
    Cel
    0.08
    Marked
    0.08
    Tw
    0.07
    _neg
    0.07
     alcan
    0.07
     reject
    0.07
    Job
    0.07
     위험
    0.07
    Activations Density 0.002%

    No Known Activations