© 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. 51225
    Prev
    Next
    INDEX
    Explanations

    the

    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
     ratios
    -0.12
     rays
    -0.11
    _rat
    -0.11
     Rays
    -0.10
    Cycles
    -0.10
    _cycles
    -0.10
     races
    -0.09
    rat
    -0.09
    _batches
    -0.09
    cycles
    -0.09
    POSITIVE LOGITS
     segment
    0.23
    segment
    0.20
     separation
    0.19
    Segment
    0.18
    _segment
    0.18
     chord
    0.18
     Segment
    0.18
    .segment
    0.17
    (segment
    0.16
     segmento
    0.16
    Activations Density 0.226%

    No Known Activations