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. 65195
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    公
    -0.09
     fu
    -0.08
    [C
    -0.08
    zu
    -0.08
     прид
    -0.08
    -Regular
    -0.08
    gegen
    -0.07
     ک
    -0.07
    Against
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     intangible
    0.10
     futuristic
    0.08
     pse
    0.08
     связанные
    0.08
     Traum
    0.08
     Vogel
    0.07
     Robinson
    0.07
     Rip
    0.07
     Alec
    0.07
     Luk
    0.07
    Activations Density 0.077%

    No Known Activations