© 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. 24734
    Prev
    Next
    INDEX
    Explanations

    weighting

    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
     তাক
    -0.08
     abas
    -0.07
     kar
    -0.07
     સપ
    -0.07
     Electric
    -0.07
     stal
    -0.07
     વર્ષ
    -0.07
     тұ
    -0.07
    ucar
    -0.07
     вп
    -0.07
    POSITIVE LOGITS
     weighting
    0.18
    .weights
    0.18
     weights
    0.16
    .weight
    0.15
    weights
    0.14
     weighted
    0.14
    (weight
    0.14
     weight
    0.14
    _weights
    0.14
     वजन
    0.14
    Activations Density 0.012%

    No Known Activations