© 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. 49331
    Prev
    Next
    INDEX
    Explanations

    ending in 29

    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
     Gob
    -0.08
    trs
    -0.08
     Gum
    -0.08
    Gob
    -0.08
     lenguaje
    -0.08
    trico
    -0.08
     lone
    -0.07
     spo
    -0.07
     trolls
    -0.07
     sgr
    -0.07
    POSITIVE LOGITS
    29
    0.17
    029
    0.14
    329
    0.14
    829
    0.13
    629
    0.13
    229
    0.12
    529
    0.12
    929
    0.12
    729
    0.11
    129
    0.10
    Activations Density 0.043%

    No Known Activations