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. 77223
    Prev
    Next
    INDEX
    Explanations

    accuracy

    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
    .lang
    -0.07
    /full
    -0.07
     extinct
    -0.07
     extinction
    -0.07
     agres
    -0.07
     existe
    -0.07
     possibilities
    -0.07
    zie
    -0.07
    riors
    -0.07
     existir
    -0.07
    POSITIVE LOGITS
     accuracy
    0.10
     factual
    0.10
    Accuracy
    0.10
     Accuracy
    0.10
     grammatical
    0.09
     inaccuracies
    0.09
    accuracy
    0.09
     акту
    0.09
     misinformation
    0.09
    accur
    0.09
    Activations Density 0.024%

    No Known Activations