Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18908
    Prev
    Next
    INDEX
    Explanations

    code related texts

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     למשל
    -0.09
    เงินฟรี
    -0.09
     feadh
    -0.09
    ลงทะเบียนฟรี
    -0.09
     masiku
    -0.09
     миллӣ
    -0.09
    өлөр
    -0.09
     להס
    -0.09
    imhse
    -0.09
    احث
    -0.09
    POSITIVE LOGITS
    ?
    0.08
    ?"
    0.08
    "
    0.08
    x
    0.08
    "?
    0.08
    0
    0.08
    “
    0.08
    H
    0.08
    SIN
    0.08
    ,
    0.07
    Activations Density 0.097%

    No Known Activations