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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23420
    Prev
    Next
    INDEX
    Explanations

    B

    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
     düşünd
    -0.08
    การแข่งขัน
    -0.08
     disadv
    -0.08
    iciencies
    -0.08
    ுவ
    -0.08
    صفات
    -0.08
    ാടക
    -0.08
     Fais
    -0.08
    iciente
    -0.08
    了一等奖
    -0.08
    POSITIVE LOGITS
    .js
    0.08
     revert
    0.08
     ng
    0.08
     Kling
    0.07
     domicilio
    0.07
    ng
    0.07
    .emb
    0.07
    imer
    0.07
     nginx
    0.07
     curl
    0.07
    Activations Density 0.004%

    No Known Activations