© 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. 114
    Prev
    Next
    INDEX
    Explanations

    indirectly

    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
    favorite
    -0.08
     favorit
    -0.08
     individualized
    -0.08
     particuli
    -0.08
     iki
    -0.08
     پسند
    -0.08
    favorites
    -0.08
    ($.
    -0.08
     $↵
    -0.08
     Speed
    -0.07
    POSITIVE LOGITS
     indirectly
    0.23
     indirect
    0.21
    Indirect
    0.21
     indire
    0.16
     INDIRECT
    0.13
    irect
    0.12
     proxy
    0.11
    Proxy
    0.10
     broader
    0.09
    proxy
    0.09
    Activations Density 0.098%

    No Known Activations