© 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. 97441
    Prev
    Next
    INDEX
    Explanations

    Try

    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
    estions
    -0.08
    ative
    -0.07
     Schlag
    -0.07
     hiermee
    -0.07
    ENS
    -0.07
    قتها
    -0.07
    _metrics
    -0.07
     extensive
    -0.07
     Nick
    -0.07
    _points
    -0.07
    POSITIVE LOGITS
    DEA
    0.09
    ol
    0.08
    μή
    0.08
    μη
    0.08
    ол
    0.08
    ape
    0.07
    jes
    0.07
    USA
    0.07
     pct
    0.07
     dejó
    0.07
    Activations Density 0.002%

    No Known Activations