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. 58663
    Prev
    Next
    INDEX
    Explanations

    dark energy and physics

    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
     intake
    -0.08
    -0.08
    recent
    -0.07
    √
    -0.07
    Stmt
    -0.07
     hepatic
    -0.07
    stride
    -0.07
    র্ব
    -0.07
     Balkan
    -0.07
    属
    -0.07
    POSITIVE LOGITS
     poesía
    0.09
     hierbij
    0.09
    άν
    0.09
     Poems
    0.08
    _canvas
    0.08
     sond
    0.08
     Beaut
    0.08
     jardins
    0.08
     Bondye
    0.08
     Automaten
    0.08
    Activations Density 0.001%

    No Known Activations