© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6720
    Prev
    Next
    INDEX
    Explanations

    Cradling

    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
     paint
    -0.09
    .paint
    -0.09
     cd
    -0.08
    CD
    -0.08
     retras
    -0.08
     pronta
    -0.08
    He's
    -0.08
     characterised
    -0.08
     colores
    -0.07
     duplicated
    -0.07
    POSITIVE LOGITS
     淮
    0.09
     IK
    0.09
    stüt
    0.09
    istik
    0.09
    mein
    0.08
     Groningen
    0.08
     fetal
    0.08
    un
    0.07
    RAD
    0.07
    ليب
    0.07
    Activations Density 0.000%

    No Known Activations