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. 119325
    Prev
    Next
    INDEX
    Explanations

    Math and logic

    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
    .rh
    -0.07
    _ro
    -0.07
     Hud
    -0.07
     bez
    -0.07
    hatian
    -0.07
     همچنین
    -0.07
     Entwicklung
    -0.07
    .ro
    -0.07
     jaune
    -0.07
     reliably
    -0.07
    POSITIVE LOGITS
     इंड
    0.08
     indist
    0.08
     kës
    0.07
     passports
    0.07
     ficou
    0.07
    aster
    0.07
     дат
    0.07
     डेट
    0.07
     وضع
    0.07
    items
    0.07
    Activations Density 0.014%

    No Known Activations