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. 102959
    Prev
    Next
    INDEX
    Explanations

    Doing/creating

    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
     Basics
    -0.08
     ça
    -0.08
    Basics
    -0.08
    ley
    -0.07
    Mill
    -0.07
    éb
    -0.07
    级
    -0.07
    -au
    -0.07
    Occup
    -0.07
    大的
    -0.07
    POSITIVE LOGITS
    રે
    0.09
    ંત્ર
    0.08
    તે
    0.07
    (util
    0.07
    חשב
    0.07
    응
    0.07
     esquina
    0.07
    175
    0.07
     BLO
    0.07
     proprie
    0.07
    Activations Density 0.368%

    No Known Activations