© 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. 54914
    Prev
    Next
    INDEX
    Explanations

    a

    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
     drôle
    -0.08
    .mk
    -0.07
    .tsv
    -0.07
    なお
    -0.07
     upset
    -0.07
    以内
    -0.07
    icke
    -0.07
    (strcmp
    -0.07
    iety
    -0.07
     presumably
    -0.07
    POSITIVE LOGITS
     будто
    0.10
     berikut
    0.08
     unto
    0.08
    银
    0.08
     helpless
    0.08
     Quentin
    0.08
    Arn
    0.08
     Silver
    0.08
     bäst
    0.07
     homage
    0.07
    Activations Density 0.030%

    No Known Activations