© 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. 23-RESID-POST-AA
    11. 48024
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lot
    -0.09
     phenomenon
    -0.08
     sesuatu
    -0.07
    -left
    -0.07
    /sh
    -0.07
     notion
    -0.07
    ous
    -0.07
    enario
    -0.07
    ";
    -0.07
    able
    -0.07
    POSITIVE LOGITS
     whim
    0.15
     nearby
    0.14
     windy
    0.13
     deserted
    0.13
     sunny
    0.13
     rainy
    0.12
     crowded
    0.11
     secluded
    0.11
     unsus
    0.11
     annars
    0.11
    Activations Density 0.040%

    No Known Activations