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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43727
    Prev
    Next
    INDEX
    Explanations

    feelings

    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
     hierdoor
    -0.08
    _WITH
    -0.08
    adang
    -0.08
    ��
    -0.08
     flying
    -0.08
     känna
    -0.07
     희
    -0.07
     exhilar
    -0.07
    CTYPE
    -0.07
    pta
    -0.07
    POSITIVE LOGITS
    策
    0.07
    メール
    0.07
    磨
    0.07
    セル
    0.07
    zugeben
    0.07
     POST
    0.07
    	sort
    0.07
     подраздел
    0.07
    subst
    0.07
    hamento
    0.07
    Activations Density 0.001%

    No Known Activations