© 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. 8094
    Prev
    Next
    INDEX
    Explanations

    ctl

    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
     Because
    -0.08
    Because
    -0.07
    .Public
    -0.07
    Below
    -0.07
    ILS
    -0.07
    herent
    -0.06
     Below
    -0.06
    කි
    -0.06
     Without
    -0.06
     desperate
    -0.06
    POSITIVE LOGITS
     morgens
    0.08
    FAST
    0.08
     overview
    0.08
     Yah
    0.08
    ━━
    0.08
     humm
    0.08
    候
    0.08
    ढ़
    0.08
    VIDER
    0.08
     analis
    0.08
    Activations Density 0.001%

    No Known Activations