© 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. 11-RESID-POST-AA
    11. 63258
    Prev
    Next
    INDEX
    Explanations

    arm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     formative
    -0.09
    Pap
    -0.08
     alte
    -0.08
     compétence
    -0.08
    َال
    -0.07
     schnelle
    -0.07
    ि�
    -0.07
    迅
    -0.07
    (con
    -0.07
     Buiten
    -0.07
    POSITIVE LOGITS
    ledem
    0.08
     xa
    0.08
    armen
    0.08
     Coast
    0.08
     سبق
    0.08
    odox
    0.07
     yas
    0.07
     тоже
    0.07
    <Car
    0.07
     플랫폼
    0.07
    Activations Density 0.000%

    No Known Activations