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. 23408
    Prev
    Next
    INDEX
    Explanations

    code

    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
     hide
    -0.08
    niž
    -0.08
    _Pl
    -0.08
    	hide
    -0.07
     evade
    -0.07
     gian
    -0.07
     accommodates
    -0.07
    ­↵
    -0.07
    .escape
    -0.07
     Essex
    -0.07
    POSITIVE LOGITS
    Operands
    0.08
    allu
    0.08
    halb
    0.08
    iry
    0.07
    kl
    0.07
    Operand
    0.07
    klju
    0.07
     améric
    0.07
    huizen
    0.07
     acontecimentos
    0.07
    Activations Density 0.000%

    No Known Activations