© 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. 50639
    Prev
    Next
    INDEX
    Explanations

    lists of numbers

    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
    307
    -0.09
    282
    -0.09
    dad
    -0.09
    old
    -0.08
    280
    -0.08
    detect
    -0.08
    271
    -0.08
    306
    -0.08
    Goed
    -0.08
    Detect
    -0.08
    POSITIVE LOGITS
    百科
    0.09
     realiza
    0.08
     estratég
    0.08
     declara
    0.08
     schop
    0.08
     coloca
    0.08
     khả
    0.07
     रणनी
    0.07
     quiero
    0.07
    _micro
    0.07
    Activations Density 0.007%

    No Known Activations