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. 11-RESID-POST-AA
    6. 42105
    Prev
    Next
    INDEX
    Explanations

    IDs and codes

    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
     Demi
    -0.08
     göst
    -0.08
     divent
    -0.08
    天地
    -0.08
     aikaan
    -0.08
     együtt
    -0.08
     söyle
    -0.08
    产业
    -0.08
    llll
    -0.08
     nuance
    -0.07
    POSITIVE LOGITS
     numbering
    0.09
     번호
    0.08
     запис
    0.08
     Baz
    0.08
    _IDS
    0.08
    番号
    0.08
    번호
    0.08
    编号
    0.08
    號
    0.08
     PK
    0.08
    Activations Density 0.015%

    No Known Activations