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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 95148
    Prev
    Next
    INDEX
    Explanations

    disallowed actions

    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
    cert
    -0.09
     admittedly
    -0.08
     Special
    -0.08
     חשוב
    -0.08
    érés
    -0.08
     fontos
    -0.07
     Coins
    -0.07
     활용
    -0.07
     cautiously
    -0.07
     Handmade
    -0.07
    POSITIVE LOGITS
     unless
    0.09
     nor
    0.09
     sequer
    0.09
    unless
    0.09
     zomaar
    0.09
     ilyen
    0.08
    238
    0.08
    เด็ด
    0.08
    nor
    0.08
     excessive
    0.08
    Activations Density 0.031%

    No Known Activations