© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18678
    Prev
    Next
    INDEX
    Explanations

    sir

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    галтер
    -0.09
    колько
    -0.09
    одатель
    -0.08
     tarkoit
    -0.08
    置
    -0.08
    важа
    -0.08
    ుకొ
    -0.08
    ылығы
    -0.08
    алт
    -0.08
     پو
    -0.08
    POSITIVE LOGITS
    loin
    0.12
    acuse
    0.11
    enix
    0.10
    soe
    0.10
    ens
    0.10
    red
    0.09
    iously
    0.09
    inals
    0.09
    ahs
    0.09
    viendo
    0.09
    Activations Density 0.002%

    No Known Activations