Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18903
    Prev
    Next
    INDEX
    Explanations

    :

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provavelmente
    -0.09
     herself
    -0.08
     probablemente
    -0.08
    Designer
    -0.08
     따른
    -0.08
    Lister
    -0.08
     retail
    -0.07
     дизайнер
    -0.07
     designer
    -0.07
     인간
    -0.07
    POSITIVE LOGITS
    100
    0.11
    40
    0.11
    760
    0.09
    20
    0.09
    102
    0.09
    10
    0.09
    70
    0.09
    300
    0.09
    200
    0.09
    50
    0.09
    Activations Density 0.004%

    No Known Activations