© 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. 50919
    Prev
    Next
    INDEX
    Explanations

    band

    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
    ति
    -0.09
    uments
    -0.08
    мой
    -0.08
    оже
    -0.08
    исс
    -0.08
    omst
    -0.08
    дох
    -0.08
    athers
    -0.08
     душе
    -0.08
    ashes
    -0.08
    POSITIVE LOGITS
    -a
    0.09
    -A
    0.09
    icam
    0.09
     aiding
    0.09
     aid
    0.09
     Aid
    0.09
    blocked
    0.09
    erol
    0.08
    erb
    0.08
    Aid
    0.08
    Activations Density 0.003%

    No Known Activations