© 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. 71116
    Prev
    Next
    INDEX
    Explanations

    opposite

    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
    ชม
    -0.08
     đông
    -0.08
    -even
    -0.08
    -qu
    -0.08
     Fitzgerald
    -0.08
    urun
    -0.08
    (ma
    -0.07
    окол
    -0.07
    ACION
    -0.07
     umr
    -0.07
    POSITIVE LOGITS
     cargo
    0.08
    Cargo
    0.08
     cargos
    0.08
     satellites
    0.08
     ಪ್ರಶ್ನ
    0.07
     ನಿಯ
    0.07
    ilia
    0.07
     LEDs
    0.07
    ailable
    0.07
    iliary
    0.07
    Activations Density 0.005%

    No Known Activations