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. 56280
    Prev
    Next
    INDEX
    Explanations

    up

    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
    Operational
    -0.08
     fruta
    -0.07
     operational
    -0.07
     kani
    -0.07
     transition
    -0.07
     distinta
    -0.07
    velden
    -0.07
     perfe
    -0.07
    -0.07
     Hind
    -0.07
    POSITIVE LOGITS
     outspoken
    0.13
     injustice
    0.12
    勇
    0.11
     ضد
    0.11
     condemnation
    0.11
    against
    0.11
     injust
    0.10
     courageous
    0.10
     boldly
    0.10
     علیه
    0.10
    Activations Density 0.055%

    No Known Activations