© 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. 11-RESID-POST-AA
    11. 68086
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ambu
    -0.07
    -large
    -0.07
     tooth
    -0.07
    郎
    -0.07
     large
    -0.07
    gnu
    -0.07
     finit
    -0.07
    ichtet
    -0.07
    lemma
    -0.07
    large
    -0.07
    POSITIVE LOGITS
     sehari
    0.09
    _daily
    0.09
     ежеднев
    0.09
     apres
    0.09
     danes
    0.09
     اليوم
    0.09
     mornings
    0.09
     weekdays
    0.08
     اليومية
    0.08
     দৈ
    0.08
    Activations Density 0.002%

    No Known Activations