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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98416
    Prev
    Next
    INDEX
    Explanations

    un

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ostr
    -0.08
     Morena
    -0.08
     presup
    -0.07
     intenta
    -0.07
     inten
    -0.07
     sw
    -0.07
    productive
    -0.07
     Academ
    -0.07
     Odin
    -0.07
     wield
    -0.07
    POSITIVE LOGITS
    tersuch
    0.16
    terschied
    0.14
    ters
    0.12
    tere
    0.11
    ­ter
    0.11
    teren
    0.11
    term
    0.10
    bedingt
    0.10
    terre
    0.10
    tersch
    0.10
    Activations Density 0.003%

    No Known Activations