© 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. 54870
    Prev
    Next
    INDEX
    Explanations

    between and ranges

    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
     conta
    -0.08
     Rek
    -0.07
    .it
    -0.07
     Dic
    -0.07
     Transportation
    -0.07
     natur
    -0.07
    .include
    -0.07
    .touch
    -0.07
     Comit
    -0.07
     Merrill
    -0.07
    POSITIVE LOGITS
     промеж
    0.09
     kože
    0.09
     مرحلة
    0.08
     وبين
    0.08
    _between
    0.08
     לבין
    0.08
     حالت
    0.08
     intermediate
    0.08
     antara
    0.08
     intermedi
    0.08
    Activations Density 0.075%

    No Known Activations