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. 119238
    Prev
    Next
    INDEX
    Explanations

    Group combinations

    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
     Gewer
    -0.08
    .UI
    -0.08
    иев
    -0.08
    <HTMLInput
    -0.07
    িস্ত
    -0.07
     besitzen
    -0.07
     wedge
    -0.07
     gamm
    -0.07
     located
    -0.07
     slender
    -0.07
    POSITIVE LOGITS
     permutation
    0.11
     permutations
    0.11
     Rotate
    0.11
     rotates
    0.10
     alternating
    0.10
     rotation
    0.10
     vaker
    0.10
     rotations
    0.09
     shuffled
    0.09
     repeats
    0.09
    Activations Density 0.036%

    No Known Activations