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. 53159
    Prev
    Next
    INDEX
    Explanations

    boom

    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
     Penal
    -0.08
    Authorities
    -0.08
     PAS
    -0.07
     Solic
    -0.07
     Mm
    -0.07
    recipes
    -0.07
    bew
    -0.07
     Researchers
    -0.07
     Intelig
    -0.07
    Ev
    -0.07
    POSITIVE LOGITS
    大的
    0.09
    -sizing
    0.08
     молодеж
    0.08
    乔
    0.08
     chic
    0.07
    Cue
    0.07
    -and
    0.07
     rapport
    0.07
    0.07
    -grand
    0.07
    Activations Density 0.006%

    No Known Activations