© 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. 47972
    Prev
    Next
    INDEX
    Explanations

    Imagine

    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
     indication
    -0.12
     emphasis
    -0.08
     mention
    -0.08
     emphasize
    -0.08
     indicate
    -0.08
    强调
    -0.08
     Indicates
    -0.08
     indicação
    -0.08
     informations
    -0.08
     Augenmerk
    -0.08
    POSITIVE LOGITS
     scenarios
    0.15
     you're
    0.14
     себе
    0.13
     أنك
    0.13
     scénario
    0.13
     yourself
    0.12
     escenarios
    0.12
     plausible
    0.12
     scenario
    0.12
    Scenario
    0.12
    Activations Density 0.031%

    No Known Activations