© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7963
    Prev
    Next
    INDEX
    Explanations

    value

    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
    upra
    -0.08
    ок
    -0.08
    Con
    -0.07
    beat
    -0.07
    Convention
    -0.07
    jeuner
    -0.07
    íl
    -0.07
    .Con
    -0.07
    Christ
    -0.07
     вен
    -0.07
    POSITIVE LOGITS
     ڊ
    0.10
     disponibili
    0.09
     SBM
    0.08
     saddle
    0.08
     rispetto
    0.08
    _prompt
    0.08
     wykorzyst
    0.07
     sco
    0.07
     bakeng
    0.07
    ként
    0.07
    Activations Density 0.005%

    No Known Activations