© 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. 3-RESID-POST-AA
    11. 3065
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الصحة
    -0.08
     под
    -0.08
     Avenida
    -0.07
     zehn
    -0.07
     öndür
    -0.07
     tř
    -0.07
     കട
    -0.07
     yaliy
    -0.07
     gy
    -0.07
     Gest
    -0.07
    POSITIVE LOGITS
    fk
    0.09
    lift
    0.08
    Decode
    0.08
     Lift
    0.07
     mutil
    0.07
    �
    0.07
    Lift
    0.07
    Sphere
    0.07
     Minority
    0.07
    decode
    0.07
    Activations Density 0.000%

    No Known Activations