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. 52835
    Prev
    Next
    INDEX
    Explanations

    ambiguity interpretation

    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
     Pride
    -0.07
    �
    -0.07
    分
    -0.07
     cul
    -0.06
     snapshot
    -0.06
     pr
    -0.06
     que
    -0.06
     стат
    -0.06
     handic
    -0.06
     razor
    -0.06
    POSITIVE LOGITS
     Лучше
    0.10
     interpretación
    0.10
     సంప
    0.09
     interpretation
    0.09
     interpreta
    0.09
    interpre
    0.09
     ambiguity
    0.09
     Interpretation
    0.09
     préférable
    0.09
     interpretations
    0.09
    Activations Density 0.123%

    No Known Activations