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. 59819
    Prev
    Next
    INDEX
    Explanations

    profile pictures

    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
    .stdout
    -0.09
     asshole
    -0.08
     stdout
    -0.08
     Españ
    -0.08
     Zwischen
    -0.08
     badan
    -0.08
     Tras
    -0.07
    losen
    -0.07
    essions
    -0.07
    stdout
    -0.07
    POSITIVE LOGITS
    ρει
    0.08
     referência
    0.07
     pubblic
    0.07
     pública
    0.07
    Cons
    0.07
    림
    0.07
    ાહ
    0.07
     שם
    0.07
    েয়ে
    0.07
     lá
    0.07
    Activations Density 0.007%

    No Known Activations