© 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. 23-RESID-POST-AA
    11. 51621
    Prev
    Next
    INDEX
    Explanations

    hyphens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    320
    -0.08
     beschäft
    -0.08
    volved
    -0.08
    350
    -0.08
    iyon
    -0.08
    ಿಯ
    -0.07
    _deg
    -0.07
    .bits
    -0.07
    रत
    -0.07
     justification
    -0.07
    POSITIVE LOGITS
     conm
    0.08
     urinary
    0.08
    Loans
    0.08
     televisión
    0.08
     lov
    0.08
     лу
    0.08
     urine
    0.08
     로그
    0.08
     lymph
    0.07
     linens
    0.07
    Activations Density 0.002%

    No Known Activations