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. 45243
    Prev
    Next
    INDEX
    Explanations

    a

    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
    terrain
    -0.08
    eker
    -0.08
     marched
    -0.08
    úrg
    -0.08
     اعمال
    -0.08
    amanya
    -0.08
    normal
    -0.08
    usetzen
    -0.08
    	set
    -0.07
     Reifen
    -0.07
    POSITIVE LOGITS
     dining
    0.09
    �
    0.09
     ambiance
    0.08
     Prepare
    0.08
     कला
    0.08
    しゃれ
    0.08
     decorative
    0.07
     POV
    0.07
     மக்கள்
    0.07
     strolling
    0.07
    Activations Density 0.025%

    No Known Activations