© 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. 24718
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
     lâu
    -0.08
    .Serialization
    -0.08
     طويل
    -0.08
     carriage
    -0.08
    リーズ
    -0.08
    Тол
    -0.08
     Serialized
    -0.07
    Delivered
    -0.07
    .serial
    -0.07
     maatschappij
    -0.07
    POSITIVE LOGITS
     Ryzen
    0.08
     후보
    0.08
     defendants
    0.08
     intimid
    0.08
     youtube
    0.08
    .lwjgl
    0.08
    (candidate
    0.08
     sospe
    0.08
     spooky
    0.07
     spoof
    0.07
    Activations Density 0.001%

    No Known Activations