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. 58422
    Prev
    Next
    INDEX
    Explanations

    computer ports

    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
     tuberculosis
    -0.09
     Alger
    -0.09
     tedious
    -0.08
     Quart
    -0.08
     Reforma
    -0.08
     Guangdong
    -0.08
     issuance
    -0.07
    vacc
    -0.07
     gar
    -0.07
    ertet
    -0.07
    POSITIVE LOGITS
    .requires
    0.08
    -stack
    0.07
    FF
    0.07
     stack
    0.07
     needs
    0.07
    .Library
    0.07
    .Deep
    0.07
    .Attach
    0.07
     lán
    0.07
     Peter
    0.07
    Activations Density 0.000%

    No Known Activations