© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 94863
    Prev
    Next
    INDEX
    Explanations

    pointers

    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
    .csv
    -0.08
    .Generated
    -0.08
    _energy
    -0.08
    Energy
    -0.08
     bred
    -0.08
     tire
    -0.08
    努力
    -0.08
    .energy
    -0.08
     toot
    -0.08
     gestaltet
    -0.07
    POSITIVE LOGITS
     uintptr
    0.16
    uintptr
    0.13
    addr
    0.12
     addr
    0.12
    (pointer
    0.11
     DWORD
    0.11
     pointers
    0.11
     intptr
    0.11
    .addr
    0.11
    _addr
    0.11
    Activations Density 0.007%

    No Known Activations