© 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 EvalsExportsAPI 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. 49925
    Prev
    Next
    INDEX
    Explanations

    Dynamics 365

    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
    -chair
    -0.09
    emmin
    -0.09
    shock
    -0.08
    kick
    -0.08
    lasses
    -0.08
    chair
    -0.08
    share
    -0.08
    Kick
    -0.08
    -share
    -0.08
     malloc
    -0.08
    POSITIVE LOGITS
     GP
    0.13
    365
    0.12
     NAV
    0.11
    _GP
    0.10
     AX
    0.10
     गुरु
    0.09
    NAV
    0.09
     GCSE
    0.09
    .Nav
    0.09
    GP
    0.09
    Activations Density 0.002%

    No Known Activations