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. 76496
    Prev
    Next
    INDEX
    Explanations

    vertex

    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
    transpose
    -0.09
    เน
    -0.08
    なお
    -0.08
    _ylim
    -0.08
    tral
    -0.08
     Karen
    -0.07
    _ylabel
    -0.07
    amy
    -0.07
     SIM
    -0.07
     diapers
    -0.07
    POSITIVE LOGITS
    .ff
    0.08
     CNT
    0.07
     Ghost
    0.07
     PTO
    0.07
     Mitt
    0.07
    Ghost
    0.07
     Local
    0.07
     enh
    0.07
     ID
    0.07
    727
    0.07
    Activations Density 0.002%

    No Known Activations