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. 3-RESID-POST-AA
    6. 12214
    Prev
    Next
    INDEX
    Explanations

    $:

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    の場合
    -0.09
    371
    -0.08
     Sierra
    -0.07
     Sendo
    -0.07
    Freq
    -0.07
    -0.07
     digging
    -0.07
    _ENCODING
    -0.07
     Cong
    -0.07
     anecd
    -0.07
    POSITIVE LOGITS
    简称
    0.08
    以下简称
    0.08
     mo
    0.08
    čer
    0.07
     ISC
    0.07
     Jessie
    0.07
     lach
    0.07
     Wah
    0.07
     vaj
    0.07
    hanger
    0.07
    Activations Density 0.083%

    No Known Activations