© 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. 50618
    Prev
    Next
    INDEX
    Explanations

    KR

    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
    teros
    -0.09
    дегі
    -0.09
     parce
    -0.09
     prič
    -0.09
    də
    -0.08
    ferencing
    -0.08
    ्टर
    -0.08
     amath
    -0.08
     Parce
    -0.08
    kere
    -0.08
    POSITIVE LOGITS
    abs
    0.12
    abba
    0.10
    abby
    0.10
    Abs
    0.10
    ాబు
    0.10
    ABS
    0.09
    abbing
    0.09
    ab
    0.09
    obby
    0.08
     бух
    0.08
    Activations Density 0.001%

    No Known Activations