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. 49030
    Prev
    Next
    INDEX
    Explanations

    creat

    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
     زی
    -0.07
     victims
    -0.07
     Proposition
    -0.07
    gig
    -0.07
    _faces
    -0.07
     faces
    -0.07
     preschool
    -0.07
    _behavior
    -0.07
    ists
    -0.07
     vertices
    -0.07
    POSITIVE LOGITS
     reserves
    0.08
     Trial
    0.08
     Installed
    0.08
     kinase
    0.08
     amm
    0.08
     concord
    0.08
     explicado
    0.08
     reserve
    0.08
     instalada
    0.07
     installeren
    0.07
    Activations Density 0.001%

    No Known Activations