© 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. 2658
    Prev
    Next
    INDEX
    Explanations

    Finding or obtaining something

    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
     lumen
    -0.08
     lum
    -0.07
     algemeen
    -0.07
     hinaus
    -0.07
     keres
    -0.07
     delim
    -0.07
     doctoral
    -0.07
     Pg
    -0.07
     amps
    -0.07
    ’ég
    -0.07
    POSITIVE LOGITS
     unve
    0.07
    syn
    0.07
    CX
    0.07
    .rs
    0.07
    UX
    0.07
     bodybuilding
    0.07
     കള
    0.07
     convolution
    0.07
    飲
    0.07
    =config
    0.07
    Activations Density 0.023%

    No Known Activations