© 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. 51161
    Prev
    Next
    INDEX
    Explanations

    Technical documentation in Russian

    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
    _DOWNLOAD
    -0.09
    _FILES
    -0.09
     colega
    -0.08
     Resolve
    -0.08
     любовь
    -0.08
    .discovery
    -0.08
    ுட
    -0.08
    _CAPTURE
    -0.08
     الرسول
    -0.08
    _operation
    -0.08
    POSITIVE LOGITS
    amme
    0.08
    most
    0.07
     Paral
    0.07
    lx
    0.07
     mote
    0.07
    ('-',
    0.07
    (outputs
    0.07
    Vol
    0.07
    oly
    0.07
    Hole
    0.07
    Activations Density 0.000%

    No Known Activations