© 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. 3-RESID-POST-AA
    11. 12928
    Prev
    Next
    INDEX
    Explanations

    garlic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concret
    -0.08
    cept
    -0.08
     fret
    -0.07
     restful
    -0.07
     TA
    -0.07
     palms
    -0.07
     conducts
    -0.07
     antique
    -0.07
    (`#
    -0.07
     Outfit
    -0.07
    POSITIVE LOGITS
     Dawson
    0.08
     Reynolds
    0.07
     большой
    0.07
    rift
    0.07
    REV
    0.07
    usch
    0.07
     простран
    0.07
    Pid
    0.07
     המקומ
    0.07
     داشته
    0.07
    Activations Density 0.001%

    No Known Activations