© 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. 102701
    Prev
    Next
    INDEX
    Explanations

    Code syntax

    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
    !“
    -0.09
     cuarta
    -0.09
     grosse
    -0.09
     selle
    -0.08
    Colorado
    -0.08
     filmmaking
    -0.08
    ¡¡
    -0.08
     méid
    -0.08
     largeur
    -0.08
    !!!!↵
    -0.08
    POSITIVE LOGITS
     (
    0.15
     &
    0.11
     &(
    0.10
    (&
    0.10
    (buffer
    0.10
     buffer
    0.10
    (reinterpret
    0.09
    ((
    0.09
     ((
    0.09
    (buf
    0.09
    Activations Density 0.002%

    No Known Activations