© 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. 97211
    Prev
    Next
    INDEX
    Explanations

    �

    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
    .Request
    -0.09
    .Name
    -0.08
    .Flags
    -0.08
     flames
    -0.08
    .Groups
    -0.08
    .Cal
    -0.08
    licts
    -0.08
    .Fire
    -0.08
    .api
    -0.08
     interactive
    -0.08
    POSITIVE LOGITS
    �
    0.16
    ൂ
    0.08
    ଙ
    0.08
    ptr
    0.08
    ૂ
    0.08
     vitamin
    0.07
    п
    0.07
    team
    0.07
    onge
    0.07
     verkef
    0.07
    Activations Density 0.002%

    No Known Activations