© 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. 97785
    Prev
    Next
    INDEX
    Explanations

    原

    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
     інших
    -0.08
     carretera
    -0.08
     ces
    -0.07
    ّه
    -0.07
     assertions
    -0.07
    GLE
    -0.07
     cão
    -0.07
     Вик
    -0.07
     Erika
    -0.07
    achment
    -0.07
    POSITIVE LOGITS
    abba
    0.08
     barrels
    0.08
    rp
    0.08
    meg
    0.07
     wat
    0.07
    raeg
    0.07
    fac
    0.07
    Pl
    0.07
    <R
    0.07
    RF
    0.07
    Activations Density 0.001%

    No Known Activations