© 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. 1429
    Prev
    Next
    INDEX
    Explanations

    names/characters

    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
    Masks
    -0.08
    PS
    -0.07
     ONU
    -0.07
     coil
    -0.07
    .MOD
    -0.07
     MOD
    -0.07
     mask
    -0.07
    lices
    -0.07
     ร
    -0.07
    +-+-+-+-
    -0.07
    POSITIVE LOGITS
     incid
    0.08
    나는
    0.08
     Arbeitgeber
    0.08
     Keeper
    0.08
    akan
    0.07
     unwanted
    0.07
    mak
    0.07
     sightings
    0.07
     anthrop
    0.07
     paras
    0.07
    Activations Density 0.534%

    No Known Activations