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. 74411
    Prev
    Next
    INDEX
    Explanations

    relation

    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
    Assessment
    -0.08
    Mac
    -0.08
     assessment
    -0.08
     Mac
    -0.08
     맞
    -0.07
    mac
    -0.07
     reconstruction
    -0.07
    -focused
    -0.07
     dopamine
    -0.07
     packaging
    -0.07
    POSITIVE LOGITS
     verletzt
    0.09
     mens
    0.09
    (tbl
    0.09
     unfair
    0.09
     Predicate
    0.09
     tbody
    0.09
     Characteristics
    0.08
     Closure
    0.08
     Recipro
    0.08
     pă
    0.08
    Activations Density 0.005%

    No Known Activations