© 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. 54808
    Prev
    Next
    INDEX
    Explanations

    zero

    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
     восп
    -0.08
    ตอน
    -0.08
     letan
    -0.08
     Formatter
    -0.08
    ления
    -0.07
     Thesis
    -0.07
     Shine
    -0.07
     kär
    -0.07
     provisioning
    -0.07
    _plugin
    -0.07
    POSITIVE LOGITS
     condition
    0.08
    Sb
    0.08
    Syl
    0.08
     zákaz
    0.07
    ুভ
    0.07
    CTS
    0.07
    (!(
    0.07
    Purple
    0.07
    čnih
    0.07
    zel
    0.07
    Activations Density 0.022%

    No Known Activations