© 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. 1408
    Prev
    Next
    INDEX
    Explanations

    Lakes

    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
     ak
    -0.09
    ുപ
    -0.08
    �
    -0.08
     애
    -0.08
    ഹ
    -0.08
     Ak
    -0.08
    애
    -0.07
     neces
    -0.07
    ദ്ധ
    -0.07
     сниж
    -0.07
    POSITIVE LOGITS
    ful
    0.08
     thi
    0.08
     Bog
    0.08
     Rap
    0.08
     pun
    0.08
    roots
    0.08
    uille
    0.07
    fully
    0.07
     Ala
    0.07
    0.07
    Activations Density 0.008%
    No Known Activations