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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 30001
    Prev
    Next
    INDEX
    Explanations

    Negative constraints

    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
     весьма
    -0.09
     ರಸ್ತ
    -0.09
     ರಸ್ತೆ
    -0.09
     보다
    -0.09
     Ander
    -0.08
     довольно
    -0.08
     możliwo
    -0.08
     intuit
    -0.08
    jalanan
    -0.08
     вполне
    -0.08
    POSITIVE LOGITS
    は禁止
    0.08
     prohibited
    0.08
     nor
    0.07
     prohibition
    0.07
     isin
    0.07
     vomiting
    0.07
     unnecessary
    0.07
     disclaim
    0.07
     noh
    0.07
     vaping
    0.07
    Activations Density 0.018%

    No Known Activations