© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6309
    Prev
    Next
    INDEX
    Explanations

    Divisors and mathematical operations

    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
     sixteen
    -0.13
     eight
    -0.11
     sexta
    -0.11
     thirteen
    -0.11
     fourteen
    -0.10
    -six
    -0.10
     sixth
    -0.10
    Eight
    -0.10
     eighth
    -0.10
     six
    -0.10
    POSITIVE LOGITS
    _attributes
    0.08
     Don't
    0.07
     drives
    0.07
    _key
    0.07
     flags
    0.07
     masks
    0.07
    letters
    0.07
     letters
    0.07
    attributes
    0.07
    285
    0.07
    Activations Density 0.018%

    No Known Activations