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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11818
    Prev
    Next
    INDEX
    Explanations

    (

    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
     σκο
    -0.09
    ORITY
    -0.08
    ofence
    -0.08
    沈
    -0.08
    compagnement
    -0.07
    ANG
    -0.07
    ADR
    -0.07
    /or
    -0.07
    ുപ്പ്
    -0.07
    ccess
    -0.07
    POSITIVE LOGITS
     factorial
    0.09
     calculated
    0.09
    Calculation
    0.09
     descending
    0.09
    下載
    0.09
     계산
    0.09
     calculating
    0.08
     télécharger
    0.08
     calculation
    0.08
     numerator
    0.08
    Activations Density 0.023%

    No Known Activations