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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60875
    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
    lẹ
    -0.08
     IID
    -0.08
    ocus
    -0.08
     sheeg
    -0.07
    .Path
    -0.07
     cuidar
    -0.07
     Cleaner
    -0.07
    kọ
    -0.07
     Mede
    -0.07
    ocated
    -0.07
    POSITIVE LOGITS
     ±
    0.16
     +/-
    0.15
    ±
    0.14
     deviations
    0.14
     deviation
    0.13
     tolerate
    0.13
     tolerance
    0.13
     variance
    0.12
    Deviation
    0.12
     variability
    0.12
    Activations Density 0.030%

    No Known Activations