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. 53716
    Prev
    Next
    INDEX
    Explanations

    multilingual

    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
    estones
    -0.09
     variable
    -0.08
     Meteor
    -0.08
    37
    -0.07
     Majesty
    -0.07
     nights
    -0.07
    (variable
    -0.07
    zew
    -0.07
    mehr
    -0.07
     Moo
    -0.07
    POSITIVE LOGITS
     khỏi
    0.18
     निकल
    0.12
     বের
    0.12
    ออก
    0.12
     keluar
    0.12
     نکل
    0.11
     out
    0.11
    出来
    0.11
    掉
    0.10
    出去
    0.10
    Activations Density 0.099%

    No Known Activations