© 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. 75649
    Prev
    Next
    INDEX
    Explanations

    mathematical constants

    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
    Insets
    -0.09
    ceau
    -0.08
     vuelva
    -0.08
    免
    -0.08
     easing
    -0.08
    Hopefully
    -0.08
    abat
    -0.08
    saving
    -0.07
     locks
    -0.07
     settles
    -0.07
    POSITIVE LOGITS
     provocative
    0.09
     owl
    0.08
     Hemisphere
    0.08
    .flip
    0.08
    *(-
    0.08
     donkere
    0.08
    (request
    0.08
     (-
    0.08
     dark
    0.08
     polarity
    0.08
    Activations Density 0.051%

    No Known Activations