© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6481
    Prev
    Next
    INDEX
    Explanations

    business excerpts

    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
     can't
    -0.19
     could
    -0.18
     might
    -0.18
     cannot
    -0.17
     can
    -0.17
     will
    -0.16
     may
    -0.16
     maybe
    -0.16
     is
    -0.15
     seems
    -0.15
    POSITIVE LOGITS
    	the
    0.16
     various
    0.15
     Various
    0.14
     Strategic
    0.14
     the
    0.13
     Diverse
    0.13
     Digital
    0.13
     High
    0.13
     Local
    0.12
     다양한
    0.12
    Activations Density 0.845%

    No Known Activations