© 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. 51587
    Prev
    Next
    INDEX
    Explanations

    му

    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
    oroč
    -0.08
    ્રીય
    -0.08
    ित्व
    -0.08
    ಿಕಾ
    -0.08
    	short
    -0.08
     European
    -0.08
     접
    -0.08
     sik
    -0.08
    -European
    -0.08
     αξ
    -0.08
    POSITIVE LOGITS
    низ
    0.08
    hoog
    0.08
    pak
    0.08
     faded
    0.08
    f
    0.08
     tugev
    0.08
    ars
    0.08
    po
    0.08
     numb
    0.07
     peab
    0.07
    Activations Density 0.001%

    No Known Activations