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. 53186
    Prev
    Next
    INDEX
    Explanations

    Tunes

    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
    টা
    -0.09
    dene
    -0.08
    ೊಬ್ಬ
    -0.08
    困
    -0.08
    -headed
    -0.07
    ദേശം
    -0.07
    ัน
    -0.07
    -ou
    -0.07
     henn
    -0.07
     pathogens
    -0.07
    POSITIVE LOGITS
     Dolores
    0.08
     Lah
    0.08
    peak
    0.08
     Everton
    0.08
     viva
    0.07
     Cura
    0.07
     Stard
    0.07
    /<
    0.07
     तथा
    0.07
     Barcl
    0.07
    Activations Density 0.002%

    No Known Activations