© 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. 6348
    Prev
    Next
    INDEX
    Explanations

    technical writing snippets

    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
    istik
    -0.08
    (fname
    -0.08
    ияти
    -0.08
    ’iz
    -0.07
     خر
    -0.07
    akter
    -0.07
     bizony
    -0.07
     fasil
    -0.07
    илик
    -0.07
     fyr
    -0.07
    POSITIVE LOGITS
     PROCESS
    0.10
     Keyboard
    0.08
     gemeente
    0.08
     PRIVATE
    0.08
     SOFTWARE
    0.08
     localidad
    0.08
    -weather
    0.08
     bottles
    0.08
     Addiction
    0.08
    manufact
    0.08
    Activations Density 0.001%

    No Known Activations