© 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. 5565
    Prev
    Next
    INDEX
    Explanations

    H

    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
    ks
    -0.08
    ms
    -0.08
     crit
    -0.08
    readonly
    -0.08
    urah
    -0.08
     fetal
    -0.07
     bladder
    -0.07
     Зам
    -0.07
     kats
    -0.07
    chedules
    -0.07
    POSITIVE LOGITS
     conciencia
    0.08
     clearance
    0.08
     consciência
    0.07
     नी
    0.07
    ति
    0.07
    _RES
    0.07
    orge
    0.07
    iriya
    0.07
     tiba
    0.07
    ้อย
    0.07
    Activations Density 0.000%

    No Known Activations