© 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. 111399
    Prev
    Next
    INDEX
    Explanations

    spell

    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
    �
    -0.08
     келиш
    -0.07
    xr
    -0.07
     Ew
    -0.07
    inosaur
    -0.07
    aisse
    -0.07
     salários
    -0.07
     ואם
    -0.07
    -most
    -0.07
    ાણ
    -0.07
    POSITIVE LOGITS
     Chel
    0.08
     impreg
    0.08
    crip
    0.08
    crafted
    0.08
     crafted
    0.08
    stick
    0.07
     tad
    0.07
    bite
    0.07
    込
    0.07
     dic
    0.07
    Activations Density 0.004%

    No Known Activations