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. 88004
    Prev
    Next
    INDEX
    Explanations

    responsibility, liability

    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
    तम
    -0.08
    DBObject
    -0.07
    했고
    -0.07
     ਪ
    -0.07
     Beam
    -0.07
    농
    -0.07
    ाईं
    -0.07
    loan
    -0.07
     прог
    -0.07
     Trim
    -0.07
    POSITIVE LOGITS
     aansprak
    0.08
     referente
    0.08
     Fundación
    0.08
     wrongful
    0.08
    ાવ
    0.08
     ratione
    0.08
    gist
    0.08
    FT
    0.08
    abilir
    0.08
    -Afrika
    0.08
    Activations Density 0.008%

    No Known Activations