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. 65678
    Prev
    Next
    INDEX
    Explanations

    mathematical sets and expressions

    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
     именно
    -0.07
    placement
    -0.07
     física
    -0.07
    ouvoir
    -0.07
    ಿಕೊಳ್ಳ
    -0.07
     gesto
    -0.07
     conventions
    -0.07
    _extended
    -0.07
     rituals
    -0.07
    ôsob
    -0.07
    POSITIVE LOGITS
     minus
    0.13
    Minus
    0.11
    Except
    0.10
     except
    0.10
     excepto
    0.10
     Minus
    0.10
     Except
    0.10
    minus
    0.09
    _except
    0.09
    ంలోని
    0.08
    Activations Density 0.023%

    No Known Activations