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. 3-RESID-POST-AA
    6. 2166
    Prev
    Next
    INDEX
    Explanations

    exists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MDF
    -0.09
     theoretically
    -0.08
     fecha
    -0.08
     Kard
    -0.08
    乙
    -0.07
    折
    -0.07
     cad
    -0.07
    この
    -0.07
    -facing
    -0.07
     stip
    -0.07
    POSITIVE LOGITS
     Chim
    0.08
     पूछ
    0.08
    forum
    0.08
     Wein
    0.07
    .for
    0.07
    =mysql
    0.07
     Seren
    0.07
    .pose
    0.07
     bee
    0.07
     chim
    0.07
    Activations Density 0.001%

    No Known Activations