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. 120217
    Prev
    Next
    INDEX
    Explanations

    Internal

    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
     minority
    -0.08
     ensuring
    -0.08
     reassurance
    -0.07
     Iraq
    -0.07
     provision
    -0.07
     toplum
    -0.07
    _PROTO
    -0.07
     adap
    -0.07
     enforced
    -0.07
     adaptor
    -0.07
    POSITIVE LOGITS
    ற
    0.09
     Attractions
    0.08
    lé
    0.08
     первой
    0.08
    cheduling
    0.08
    ैले
    0.08
     сц
    0.08
     частей
    0.08
     వెల
    0.08
     Guitar
    0.08
    Activations Density 0.001%

    No Known Activations