© 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. 23-RESID-POST-AA
    11. 50125
    Prev
    Next
    INDEX
    Explanations

    session

    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
    ttes
    -0.08
    owana
    -0.08
    ционный
    -0.08
     seus
    -0.08
     नियुक्त
    -0.08
    62
    -0.08
    ứng
    -0.07
    mater
    -0.07
    ilers
    -0.07
     pis
    -0.07
    POSITIVE LOGITS
    DOM
    0.08
    DW
    0.08
     мене
    0.07
     stiffness
    0.07
     PRICE
    0.07
    IFICATION
    0.07
    Exe
    0.07
    (!(
    0.07
     cheap
    0.07
     EXP
    0.07
    Activations Density 0.000%

    No Known Activations