© 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. 6125
    Prev
    Next
    INDEX
    Explanations

    hum

    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
     komu
    -0.08
     dambe
    -0.08
     tarda
    -0.08
     user
    -0.08
     dalka
    -0.08
     ponu
    -0.08
     koma
    -0.07
     osoba
    -0.07
     duda
    -0.07
     gösterm
    -0.07
    POSITIVE LOGITS
    machines
    0.12
     machinery
    0.11
     lull
    0.11
    dies
    0.11
     incess
    0.10
    songs
    0.10
     constante
    0.10
     मशीन
    0.10
     энерг
    0.10
    machine
    0.10
    Activations Density 0.018%

    No Known Activations