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. 102763
    Prev
    Next
    INDEX
    Explanations

    graffiti

    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
    usar
    -0.08
     Gespr
    -0.08
    lič
    -0.07
     negoci
    -0.07
     houver
    -0.07
    _given
    -0.07
     вос
    -0.07
     Lik
    -0.07
     gzip
    -0.07
     advantage
    -0.07
    POSITIVE LOGITS
     graffiti
    0.10
     vandal
    0.10
    ffiti
    0.09
     Trudeau
    0.09
     verboden
    0.08
     grime
    0.08
     murals
    0.08
     prol
    0.08
    Marks
    0.08
     Guerr
    0.08
    Activations Density 0.003%

    No Known Activations