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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6132
    Prev
    Next
    INDEX
    Explanations

    Two-letter words ending in "d", "e", or "g"

    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
    rax
    -0.08
    otropic
    -0.08
     jil
    -0.08
    otro
    -0.08
    rosis
    -0.08
    pes
    -0.08
    ampling
    -0.08
    otrop
    -0.08
    anthem
    -0.08
    hej
    -0.07
    POSITIVE LOGITS
    yd
    0.08
    եմբ
    0.08
    ուբ
    0.08
     bz
    0.07
    ემბ
    0.07
    Well
    0.07
    Eva
    0.07
    ումբ
    0.07
    -e
    0.07
    емо
    0.07
    Activations Density 0.000%

    No Known Activations