© 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. 70819
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
     BL
    -0.08
     Ł
    -0.08
     rendu
    -0.07
     guard
    -0.07
     survivor
    -0.07
    BL
    -0.07
    roj
    -0.07
    �
    -0.07
     creatively
    -0.07
     tirer
    -0.07
    POSITIVE LOGITS
     wenn
    0.08
    upha
    0.08
    adeed
    0.08
    entlig
    0.08
     stout
    0.08
     "--
    0.07
    gbaar
    0.07
     cp
    0.07
    aaa
    0.07
     atal
    0.07
    Activations Density 0.002%

    No Known Activations