© 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. 23-RESID-POST-AA
    6. 97544
    Prev
    Next
    INDEX
    Explanations

    say "C"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    -0.08
    chg
    -0.08
    onal
    -0.08
    oni
    -0.08
     devi
    -0.07
    iód
    -0.07
    leme
    -0.07
    onic
    -0.07
    ?a
    -0.07
    ulem
    -0.07
    POSITIVE LOGITS
    raphics
    0.09
    raph
    0.08
     gifts
    0.08
    raphic
    0.08
    ырқ
    0.08
     подар
    0.08
    ру
    0.08
    �
    0.08
    ichí
    0.08
    事情
    0.08
    Activations Density 0.001%

    No Known Activations