© 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. 3-RESID-POST-AA
    11. 12855
    Prev
    Next
    INDEX
    Explanations

    月 (moon/month)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marshall
    -0.08
     Lac
    -0.08
     incidents
    -0.08
    taa
    -0.08
     commun
    -0.08
    Marshall
    -0.07
    .prevent
    -0.07
     occ
    -0.07
     incidence
    -0.07
    .bundle
    -0.07
    POSITIVE LOGITS
    悠
    0.08
    goto
    0.08
     valleys
    0.08
     ему
    0.08
    Mons
    0.08
     apr
    0.08
    conds
    0.07
     deserving
    0.07
     ndụ
    0.07
     hardworking
    0.07
    Activations Density 0.008%

    No Known Activations