© 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. 70509
    Prev
    Next
    INDEX
    Explanations

    less

    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
    áním
    -0.08
    tenham
    -0.08
     উত্তর
    -0.08
    leys
    -0.08
     Нат
    -0.08
    缓
    -0.08
    Tint
    -0.07
    (pl
    -0.07
    (front
    -0.07
    ិត
    -0.07
    POSITIVE LOGITS
     sat
    0.08
     juros
    0.08
     Current
    0.08
     gj
    0.08
     courant
    0.08
     bk
    0.08
    χές
    0.08
     current
    0.07
     gf
    0.07
     KO
    0.07
    Activations Density 0.000%

    No Known Activations