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. 88235
    Prev
    Next
    INDEX
    Explanations

    code, math, and foreign languages

    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
    ervice
    -0.08
    CON
    -0.08
    laden
    -0.08
     stipulated
    -0.07
    äden
    -0.07
    AF
    -0.07
     Mills
    -0.07
    мін
    -0.07
     آخ
    -0.07
     editions
    -0.07
    POSITIVE LOGITS
     swapping
    0.08
    erase
    0.08
    	swap
    0.07
    ,String
    0.07
     pile
    0.07
     hosped
    0.07
     жит
    0.07
    ,function
    0.07
     empty
    0.07
     bypass
    0.07
    Activations Density 0.000%

    No Known Activations