© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44878
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     Lec
    -0.09
     Demokrat
    -0.08
     Gerade
    -0.08
     Así
    -0.08
     печени
    -0.08
    isations
    -0.08
     chansons
    -0.08
     Representation
    -0.08
     Darstellung
    -0.07
     marchand
    -0.07
    POSITIVE LOGITS
    Rich
    0.08
     корот
    0.08
     rich
    0.08
    .Rich
    0.07
    rich
    0.07
     hoe
    0.07
    .rich
    0.07
     brief
    0.07
     cycling
    0.07
    عار
    0.07
    Activations Density 0.001%

    No Known Activations