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. 112798
    Prev
    Next
    INDEX
    Explanations

    Semantics and reference

    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
     abdomen
    -0.09
     trending
    -0.08
     adip
    -0.08
     abdominal
    -0.08
    ogados
    -0.08
     protective
    -0.08
    zych
    -0.07
    臀
    -0.07
     Protective
    -0.07
    腰
    -0.07
    POSITIVE LOGITS
     सिं
    0.10
     liar
    0.10
     utter
    0.09
     vérité
    0.09
     meanings
    0.09
     શબ્દ
    0.09
     शब्द
    0.09
     stereotype
    0.08
     Wörter
    0.08
    valuator
    0.08
    Activations Density 0.006%

    No Known Activations