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. 12039
    Prev
    Next
    INDEX
    Explanations

    text generation and translation

    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
     Situ
    -0.09
    (Pos
    -0.08
    _Pos
    -0.08
    Pos
    -0.07
    _Index
    -0.07
    Í
    -0.07
    rib
    -0.07
     �
    -0.07
     Rend
    -0.07
     □
    -0.07
    POSITIVE LOGITS
     favourite
    0.09
     favorit
    0.09
     favorite
    0.08
     bientôt
    0.08
    favorite
    0.08
     fav
    0.08
     dream
    0.08
    نام
    0.08
     favorita
    0.08
     способен
    0.08
    Activations Density 0.012%

    No Known Activations