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. 130300
    Prev
    Next
    INDEX
    Explanations

    policy violations

    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
     conservación
    -0.08
    consult
    -0.08
    _expected
    -0.08
    Solicitud
    -0.08
    规划
    -0.08
     conocidos
    -0.08
    _material
    -0.08
    quiries
    -0.08
    known
    -0.08
     terpercaya
    -0.08
    POSITIVE LOGITS
     notamment
    0.09
     sexual
    0.09
     violence
    0.08
     сексу
    0.08
     rust
    0.08
     vividly
    0.08
     കുട്ട
    0.08
     BDSM
    0.08
     apparently
    0.07
     sexuelle
    0.07
    Activations Density 0.031%

    No Known Activations