© 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. 19-RESID-POST-AA
    11. 102783
    Prev
    Next
    INDEX
    Explanations

    say "C"

    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
     railway
    -0.08
     EACH
    -0.08
    -0.08
     WERE
    -0.08
     ihrer
    -0.08
    xec
    -0.08
    gris
    -0.08
     skate
    -0.08
    .IS
    -0.08
     كلها
    -0.08
    POSITIVE LOGITS
     a
    0.10
     coefficients
    0.10
     importantly
    0.09
     (!)
    0.09
     તેથી
    0.09
     so
    0.08
    为了
    0.08
     thus
    0.08
     constat
    0.08
     resíduos
    0.08
    Activations Density 0.015%
    No Known Activations