© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    is

    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
     annotations
    -0.09
    ضمون
    -0.09
     никаких
    -0.08
     explanations
    -0.08
    тыру
    -0.08
    писание
    -0.08
     kekahi
    -0.08
     порядок
    -0.08
    'description
    -0.08
     disturbance
    -0.08
    POSITIVE LOGITS
     asking
    0.16
     aiming
    0.15
     designed
    0.14
     flawed
    0.14
     poorly
    0.13
     seeking
    0.13
     expecting
    0.13
     trying
    0.13
     intending
    0.13
     formulated
    0.13
    Activations Density 0.064%

    No Known Activations