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. 119204
    Prev
    Next
    INDEX
    Explanations

    defining phrases

    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
     satisfe
    -0.08
    strategy
    -0.08
    desc
    -0.08
    pan
    -0.07
    available
    -0.07
    -cat
    -0.07
    builder
    -0.07
     strategy
    -0.07
    _strategy
    -0.07
    fficient
    -0.07
    POSITIVE LOGITS
     ਸਮ
    0.10
    0.10
     enigmatic
    0.09
     mystérie
    0.09
     تفسير
    0.09
     ambiguous
    0.09
     సమ
    0.09
     Bedeut
    0.09
    Encounter
    0.09
     సంద
    0.09
    Activations Density 0.045%

    No Known Activations