© 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. 48228
    Prev
    Next
    INDEX
    Explanations

    است

    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
    aylor
    -0.08
    ICLES
    -0.08
    _BG
    -0.08
    LOAT
    -0.08
    $x
    -0.08
    usel
    -0.08
     floated
    -0.07
    虎
    -0.07
    ేస్త
    -0.07
    พ
    -0.07
    POSITIVE LOGITS
    لام
    0.15
    عادة
    0.14
    كمال
    0.13
    رج
    0.13
    دع
    0.12
    رد
    0.11
    بعاد
    0.11
    قبال
    0.10
    لمه
    0.10
    ظهار
    0.09
    Activations Density 0.001%

    No Known Activations