Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65926
    Prev
    Next
    INDEX
    Explanations

    =

    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
    TB
    -0.08
     eclipse
    -0.08
    概率
    -0.08
     Betrag
    -0.07
    弄
    -0.07
    冊
    -0.07
    交易
    -0.07
    STATUS
    -0.07
    Tu
    -0.07
    ξε
    -0.07
    POSITIVE LOGITS
     perch
    0.08
     vie
    0.08
     internetu
    0.07
    AIN
    0.07
     الش
    0.07
     Moody
    0.07
    алу
    0.07
     szkol
    0.07
     لیت
    0.07
    Alphabet
    0.07
    Activations Density 0.010%

    No Known Activations