© 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. 65051
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed"

    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
     residency
    -0.07
    Descriptor
    -0.07
     visu
    -0.07
    _impl
    -0.07
    직
    -0.07
     PCs
    -0.07
     blinds
    -0.07
    _Type
    -0.07
    ેશ
    -0.07
     гэтай
    -0.07
    POSITIVE LOGITS
     demeanor
    0.09
    弱
    0.09
     calmer
    0.09
    部分
    0.08
    一区
    0.08
    欣
    0.08
    0.08
     koi
    0.08
     reluctantly
    0.08
    vano
    0.08
    Activations Density 0.022%
    No Known Activations