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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7711
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
     руш
    -0.09
    .Marker
    -0.08
     padrão
    -0.08
     Quarry
    -0.08
     Admission
    -0.08
     Parc
    -0.08
     verr
    -0.08
    .Part
    -0.08
     Caso
    -0.08
     condição
    -0.08
    POSITIVE LOGITS
    Cc
    0.08
     squeeze
    0.08
    ohol
    0.08
    ff
    0.07
    gcc
    0.07
     shorten
    0.07
    Ear
    0.07
     انا
    0.07
    Nl
    0.07
     ff
    0.07
    Activations Density 0.003%

    No Known Activations