© 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. 24700
    Prev
    Next
    INDEX
    Explanations

    lists and structured information

    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
    ోవ
    -0.07
    efore
    -0.07
    avite
    -0.07
    hift
    -0.07
    _drop
    -0.07
     Line
    -0.07
     düş
    -0.07
     Architect
    -0.07
     Window
    -0.07
    OVE
    -0.07
    POSITIVE LOGITS
    -speed
    0.08
     Carlton
    0.08
     것이다
    0.08
    ယ္
    0.08
     famously
    0.08
     (!)
    0.08
    atively
    0.07
     为
    0.07
    agir
    0.07
    》，
    0.07
    Activations Density 0.610%

    No Known Activations