© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 63953
    Prev
    Next
    INDEX
    Explanations

    antibody

    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
     anthem
    -0.09
     olev
    -0.08
     redd
    -0.08
     acknowledgment
    -0.08
    మన
    -0.08
     repost
    -0.08
    cknowled
    -0.08
    /about
    -0.07
    mt
    -0.07
    mf
    -0.07
    POSITIVE LOGITS
    .abort
    0.09
     therapeut
    0.08
     hotspots
    0.08
     형태
    0.08
    vido
    0.08
     വി�
    0.08
     acr
    0.08
    цеп
    0.07
     eleg
    0.07
     flown
    0.07
    Activations Density 0.003%

    No Known Activations