© 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. 47889
    Prev
    Next
    INDEX
    Explanations

    format

    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
    aycast
    -0.08
    Logic
    -0.08
    factor
    -0.08
     calculated
    -0.08
     principles
    -0.08
     soundtrack
    -0.07
     logic
    -0.07
     principle
    -0.07
     facts
    -0.07
    اي
    -0.07
    POSITIVE LOGITS
    Specifier
    0.17
     spec
    0.16
    ting
    0.16
    ters
    0.16
    specifier
    0.16
    	spec
    0.16
     Spec
    0.14
    _spec
    0.14
    TING
    0.13
    tted
    0.13
    Activations Density 0.021%

    No Known Activations