Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56025
    Prev
    Next
    INDEX
    Explanations

    AF

    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
     Brand
    -0.08
     Palme
    -0.08
     Tre
    -0.07
     handshake
    -0.07
     Tanger
    -0.07
     Quote
    -0.07
    Natur
    -0.07
     players
    -0.07
    .sc
    -0.07
     unob
    -0.07
    POSITIVE LOGITS
     learns
    0.09
    _roi
    0.08
     polys
    0.08
    artment
    0.08
    atly
    0.08
     woes
    0.08
     learnt
    0.08
     barren
    0.08
     grossesse
    0.07
     roi
    0.07
    Activations Density 0.001%

    No Known Activations