© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48739
    Prev
    Next
    INDEX
    Explanations

    of

    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
     and
    -0.12
     from
    -0.11
     for
    -0.11
     in
    -0.11
     of
    -0.11
     to
    -0.10
     as
    -0.10
     by
    -0.10
     via
    -0.09
     (
    -0.09
    POSITIVE LOGITS
     despair
    0.14
     sorts
    0.14
     mankind
    0.13
     doom
    0.13
     righteousness
    0.13
     bravery
    0.12
     excellence
    0.12
     fate
    0.12
     gisteren
    0.12
     remembrance
    0.12
    Activations Density 0.085%

    No Known Activations