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. 56245
    Prev
    Next
    INDEX
    Explanations

    max/min

    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
     Saddle
    -0.08
    ycles
    -0.08
    Sing
    -0.08
     pedag
    -0.08
    onders
    -0.08
     Vast
    -0.07
     Trainers
    -0.07
    llo
    -0.07
    ndrome
    -0.07
    fiets
    -0.07
    POSITIVE LOGITS
    itech
    0.08
     같은
    0.08
    |max
    0.08
    이라고
    0.08
     By
    0.08
    0.07
     scm
    0.07
     którego
    0.07
    /show
    0.07
    /install
    0.07
    Activations Density 0.002%

    No Known Activations