© 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. 6105
    Prev
    Next
    INDEX
    Explanations

    dis

    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
     सेक
    -0.08
    ındaki
    -0.08
    ooli
    -0.08
     String
    -0.08
     sibling
    -0.08
    sect
    -0.07
     dm
    -0.07
     panes
    -0.07
    .alt
    -0.07
     karibu
    -0.07
    POSITIVE LOGITS
    icane
    0.09
    loge
    0.08
    Directive
    0.08
    asurer
    0.08
    Taken
    0.08
    Inverse
    0.08
    lust
    0.08
    (permission
    0.07
    _trait
    0.07
    Mant
    0.07
    Activations Density 0.000%

    No Known Activations