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. 23-RESID-POST-AA
    6. 98662
    Prev
    Next
    INDEX
    Explanations

    Le

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _dns
    -0.08
    .euler
    -0.08
    744
    -0.08
    dns
    -0.07
     eup
    -0.07
     einz
    -0.07
     ود
    -0.07
    dule
    -0.07
     DNS
    -0.07
    ineq
    -0.07
    POSITIVE LOGITS
    Bron
    0.13
    Gar
    0.08
    Joel
    0.08
    Raid
    0.08
    Crud
    0.08
    Var
    0.08
    Cra
    0.08
    Mah
    0.08
    Cold
    0.08
    President
    0.08
    Activations Density 0.001%

    No Known Activations