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. 49151
    Prev
    Next
    INDEX
    Explanations

    Female doing something

    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
     เอฟซี
    -0.07
    bea
    -0.07
     הענ
    -0.07
     verw
    -0.07
    planet
    -0.07
    iew
    -0.07
    ীয়
    -0.07
    वार
    -0.07
    yf
    -0.07
     vergeben
    -0.07
    POSITIVE LOGITS
     pill
    0.07
    ämm
    0.07
     ulang
    0.07
     cradle
    0.07
    中过
    0.07
     morar
    0.07
     Census
    0.07
     Nid
    0.07
     Residence
    0.07
     시험
    0.07
    Activations Density 0.000%

    No Known Activations