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. 105988
    Prev
    Next
    INDEX
    Explanations

    Cloud AI services

    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
     allegiance
    -0.09
     inglesa
    -0.07
     England
    -0.07
     Czech
    -0.07
     Valve
    -0.07
     dynasty
    -0.07
     Header
    -0.07
    unchecked
    -0.07
     Notify
    -0.07
     indispensable
    -0.07
    POSITIVE LOGITS
     readiness
    0.09
     cognitive
    0.09
     Hurricane
    0.08
     conducive
    0.08
     ROC
    0.08
    ROC
    0.08
    ugc
    0.08
    _kw
    0.08
     remediation
    0.08
    ognitive
    0.08
    Activations Density 0.006%

    No Known Activations