© 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. 23-RESID-POST-AA
    11. 6273
    Prev
    Next
    INDEX
    Explanations

    instructions

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sketch
    -0.09
     sketch
    -0.09
    (upload
    -0.09
    Sketch
    -0.08
    (btn
    -0.08
     Oud
    -0.08
     צילום
    -0.08
    实名
    -0.08
     Chart
    -0.08
    angk
    -0.08
    POSITIVE LOGITS
    .instructions
    0.14
     instructions
    0.13
    instructions
    0.13
    Instructions
    0.13
     instruction
    0.13
     cycles
    0.12
     Instructions
    0.12
     instrucciones
    0.12
    cycles
    0.12
    _instruction
    0.11
    Activations Density 0.005%

    No Known Activations