© 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. 1483
    Prev
    Next
    INDEX
    Explanations

    Withdraw/recede

    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
     modifying
    -0.08
     Rogers
    -0.07
     onboard
    -0.07
     PWM
    -0.07
     Predicate
    -0.07
     李
    -0.07
     decode
    -0.07
     STM
    -0.07
     Campbell
    -0.07
     mot
    -0.07
    POSITIVE LOGITS
     retreats
    0.09
     favorit
    0.08
    tabpanel
    0.08
     Retreat
    0.08
    stitut
    0.08
     fragr
    0.08
     retreat
    0.08
     "}
    0.08
    .withdraw
    0.08
     haven
    0.08
    Activations Density 0.042%

    No Known Activations