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. 3-RESID-POST-AA
    6. 2032
    Prev
    Next
    INDEX
    Explanations

    dissertation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antib
    -0.07
     cand
    -0.07
     obsolete
    -0.07
     TIG
    -0.07
     ambul
    -0.07
     candidates
    -0.07
     fringe
    -0.07
     DAR
    -0.07
    浓
    -0.06
    ושב
    -0.06
    POSITIVE LOGITS
    GU
    0.08
    Logging
    0.08
    ze
    0.07
    elope
    0.07
    pg
    0.07
    stract
    0.07
     Bud
    0.07
    Bud
    0.07
    ew
    0.07
     zy
    0.07
    Activations Density 0.001%

    No Known Activations