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. 65739
    Prev
    Next
    INDEX
    Explanations

    trailing zeros calculation

    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
     gam
    -0.08
     subjective
    -0.08
     मात्र
    -0.08
     singleton
    -0.07
     violated
    -0.07
     उपकरण
    -0.07
     buyer
    -0.07
     infiltr
    -0.07
    .CL
    -0.07
    ammen
    -0.07
    POSITIVE LOGITS
     zeros
    0.12
    Zeros
    0.11
    zeros
    0.11
     trailing
    0.09
     acidic
    0.09
     acidity
    0.09
    acid
    0.09
    xxxxx
    0.09
     acid
    0.09
     конце
    0.09
    Activations Density 0.010%

    No Known Activations