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

    Neuronpedia

    APICircuit 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. 11965
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ાણ
    -0.08
     Word
    -0.07
     opportunity
    -0.07
     slick
    -0.07
     models
    -0.07
     concentrates
    -0.06
    LC
    -0.06
    INUX
    -0.06
     lot
    -0.06
     Hardy
    -0.06
    POSITIVE LOGITS
    clin
    0.08
     outf
    0.08
    .populate
    0.08
    lid
    0.08
     bestätigt
    0.08
     �
    0.08
     âg
    0.08
    idenav
    0.08
    released
    0.07
    obald
    0.07
    Activations Density 0.044%

    No Known Activations