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. 98468
    Prev
    Next
    INDEX
    Explanations

    Mixture replacements

    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
    .integer
    -0.08
    ANTLR
    -0.08
    Happy
    -0.08
     vocation
    -0.08
    兄
    -0.08
    Stephen
    -0.08
    .family
    -0.08
    _family
    -0.08
    Brother
    -0.08
    _listing
    -0.08
    POSITIVE LOGITS
     mixtures
    0.11
     dilution
    0.11
     aliqu
    0.11
     mixing
    0.11
     rins
    0.11
     стак
    0.11
     percentual
    0.10
     mixture
    0.10
     inoc
    0.10
     syringe
    0.10
    Activations Density 0.019%

    No Known Activations