© 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. 5871
    Prev
    Next
    INDEX
    Explanations

    Blockchains

    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
     pago
    -0.09
    _pay
    -0.08
    Pago
    -0.08
    -pay
    -0.08
    “My
    -0.08
    Blk
    -0.08
    -0.08
     SOAP
    -0.07
    Oracle
    -0.07
    _Block
    -0.07
    POSITIVE LOGITS
     Card
    0.11
    Card
    0.09
    /Card
    0.09
    <Card
    0.09
     Sol
    0.09
     Cosmos
    0.09
     creates
    0.08
    (Card
    0.08
     kard
    0.08
     Ergo
    0.08
    Activations Density 0.001%
    No Known Activations