© 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. 45208
    Prev
    Next
    INDEX
    Explanations

    arcade

    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
     Fool
    -0.09
     Bale
    -0.08
     DESC
    -0.08
    Allow
    -0.08
     Ablauf
    -0.08
    Envelope
    -0.08
    blind
    -0.07
    ardonnay
    -0.07
     Allow
    -0.07
    рақ
    -0.07
    POSITIVE LOGITS
     Gef
    0.08
     exploratory
    0.08
     исправ
    0.08
     edging
    0.08
     devices
    0.08
     arcade
    0.08
     kum
    0.07
     equivalents
    0.07
    ionais
    0.07
    探索
    0.07
    Activations Density 0.004%

    No Known Activations