© 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. 75600
    Prev
    Next
    INDEX
    Explanations

    proper nouns and experiments

    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
     perfection
    -0.08
     enjoyment
    -0.08
     imgs
    -0.08
     emocional
    -0.08
     entrevist
    -0.08
     daudz
    -0.08
    _____
    -0.07
    රි
    -0.07
     accommodates
    -0.07
     menik
    -0.07
    POSITIVE LOGITS
     pioneering
    0.08
    极速
    0.08
     ACT
    0.07
     pioneers
    0.07
     fringe
    0.07
    速度
    0.07
     pioneer
    0.07
     Leiden
    0.07
    (endpoint
    0.07
    .velocity
    0.07
    Activations Density 0.092%

    No Known Activations