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. 15-RESID-POST-AA
    6. 19630
    Prev
    Next
    INDEX
    Explanations

    Neural firing patterns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     underside
    -0.09
     disclaimer
    -0.08
     disclaim
    -0.08
     ruin
    -0.08
     statute
    -0.08
     handmade
    -0.08
     angegeben
    -0.08
     ssh
    -0.08
     bash
    -0.08
     helm
    -0.08
    POSITIVE LOGITS
     firing
    0.13
     patterns
    0.12
     stereotyp
    0.11
     ensembles
    0.11
     patrones
    0.11
     excitation
    0.10
     activation
    0.10
     neurons
    0.10
     spikes
    0.10
     circuitry
    0.10
    Activations Density 0.008%

    No Known Activations