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. 90135
    Prev
    Next
    INDEX
    Explanations

    by

    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
     �
    -0.08
     možno
    -0.08
    zeption
    -0.08
    оли
    -0.07
     overrides
    -0.07
     darüber
    -0.07
    brite
    -0.07
    �
    -0.07
     برخورد
    -0.07
     Pray
    -0.07
    POSITIVE LOGITS
    Certificates
    0.07
    Cash
    0.07
    Pictures
    0.07
    al
    0.07
     sulfate
    0.07
    _sink
    0.07
    uga
    0.07
    uster
    0.07
    Balanced
    0.07
     scans
    0.07
    Activations Density 0.008%

    No Known Activations