© 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. 23-RESID-POST-AA
    11. 96738
    Prev
    Next
    INDEX
    Explanations

    scenario

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irection
    -0.09
    region
    -0.09
     region
    -0.08
     ceremony
    -0.08
    ness
    -0.08
    률
    -0.08
     daerah
    -0.08
    🏼
    -0.08
     area
    -0.08
    nesia
    -0.08
    POSITIVE LOGITS
    描述
    0.14
     waarin
    0.14
     described
    0.13
     involving
    0.13
     descr
    0.12
    -based
    0.12
    Descripción
    0.12
    Descrição
    0.12
    beschreibung
    0.12
     véc
    0.12
    Activations Density 0.040%

    No Known Activations