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. 11-RESID-POST-AA
    6. 43909
    Prev
    Next
    INDEX
    Explanations

    geometry rays

    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
    �
    -0.08
    劇
    -0.08
    بادل
    -0.07
    .encrypt
    -0.07
    laap
    -0.07
    .parse
    -0.07
    aroo
    -0.07
     پام
    -0.07
    .Box
    -0.07
     charms
    -0.07
    POSITIVE LOGITS
     Src
    0.09
    (origin
    0.08
     จุด
    0.08
    =start
    0.08
     originate
    0.08
     originates
    0.08
    künd
    0.08
     firmly
    0.08
     શરૂ
    0.08
    ,to
    0.08
    Activations Density 0.012%

    No Known Activations