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. 30043
    Prev
    Next
    INDEX
    Explanations

    inform

    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
    .ver
    -0.09
    997
    -0.09
    holder
    -0.08
    orang
    -0.08
    wanted
    -0.07
    734
    -0.07
     semper
    -0.07
    want
    -0.07
    spunkt
    -0.07
    .self
    -0.07
    POSITIVE LOGITS
     ignorant
    0.07
    �
    0.07
     Eg
    0.07
    �
    0.07
     BH
    0.07
    �
    0.07
    轩
    0.07
    函
    0.07
     Mou
    0.07
    �
    0.07
    Activations Density 0.015%

    No Known Activations