Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53265
    Prev
    Next
    INDEX
    Explanations

    long

    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
     giro
    -0.08
     Naval
    -0.08
    चल
    -0.08
    /the
    -0.08
     Boc
    -0.08
     ઘણી
    -0.08
     occident
    -0.07
     MOST
    -0.07
    Cx
    -0.07
     passa
    -0.07
    POSITIVE LOGITS
    -lasting
    0.11
    تر
    0.09
     جدًا
    0.09
    -lived
    0.09
    -standing
    0.09
    ITUDE
    0.09
    以来
    0.08
     تر
    0.08
    Enough
    0.08
    科技
    0.08
    Activations Density 0.055%

    No Known Activations