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. 43345
    Prev
    Next
    INDEX
    Explanations

    compositions

    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
    _THRESHOLD
    -0.09
    (cipher
    -0.09
    以前
    -0.09
     Coupon
    -0.08
     PICK
    -0.08
     forgive
    -0.08
    _UNLOCK
    -0.08
     破解
    -0.08
     Cipher
    -0.08
    Allocator
    -0.08
    POSITIVE LOGITS
     oraz
    0.08
     snd
    0.08
     significantly
    0.08
     styles
    0.08
     וכן
    0.08
     yes
    0.07
     शैली
    0.07
     તેમજ
    0.07
     àti
    0.07
     while
    0.07
    Activations Density 0.003%

    No Known Activations