© 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. 19-RESID-POST-AA
    11. 18703
    Prev
    Next
    INDEX
    Explanations

    find

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    క్స్
    -0.10
    сис
    -0.09
    -functions
    -0.09
    -effects
    -0.09
    -priced
    -0.09
    -म
    -0.08
    -spin
    -0.08
    -second
    -0.08
    -function
    -0.08
    -che
    -0.08
    POSITIVE LOGITS
     out
    0.42
    Out
    0.30
     Out
    0.30
    	out
    0.29
    out
    0.28
    _out
    0.27
    (out
    0.25
    -out
    0.24
    .out
    0.23
    _OUT
    0.23
    Activations Density 0.019%

    No Known Activations