© 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 EvalsExportsinterp-engineNEWAPI 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. 51036
    Prev
    Next
    INDEX
    Explanations

    壁

    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
    _dialog
    -0.09
    باح
    -0.08
    ุง
    -0.08
    itchie
    -0.07
    emor
    -0.07
    نف
    -0.07
    ಾನದ
    -0.07
     Wit
    -0.07
    ിഗ
    -0.07
     zing
    -0.07
    POSITIVE LOGITS
    �
    0.16
    炉
    0.09
    �
    0.09
    �
    0.08
    虎
    0.08
    ára
    0.08
     vert
    0.08
     Literally
    0.07
    ृत्व
    0.07
    �
    0.07
    Activations Density 0.001%

    No Known Activations