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. 56288
    Prev
    Next
    INDEX
    Explanations

    fractions and calculations

    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
    界
    -0.09
     whitespace
    -0.08
     horizon
    -0.08
     autoestima
    -0.07
     bida
    -0.07
     Hyundai
    -0.07
     halos
    -0.07
     '
    -0.07
     Santander
    -0.07
     logout
    -0.07
    POSITIVE LOGITS
     fractions
    0.16
     дроб
    0.13
    Fraction
    0.13
     fraction
    0.13
     Fraction
    0.12
     numerator
    0.12
    _fraction
    0.12
     frac
    0.12
    fraction
    0.12
     Ratio
    0.12
    Activations Density 0.231%

    No Known Activations