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. 78696
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    .session
    -0.08
    Protein
    -0.08
    protein
    -0.08
    fels
    -0.08
    _ext
    -0.08
     protein
    -0.07
     посвящ
    -0.07
    оду
    -0.07
    odian
    -0.07
     Barrett
    -0.07
    POSITIVE LOGITS
     friendliness
    0.08
    落实
    0.08
     foster
    0.08
     openness
    0.08
     budaya
    0.08
     tamen
    0.08
     ressal
    0.08
     dhex
    0.08
     sharpen
    0.08
     rzecz
    0.08
    Activations Density 0.007%

    No Known Activations