© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44821
    Prev
    Next
    INDEX
    Explanations

    hidden city flights

    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
     Hatch
    -0.08
     muffin
    -0.08
    Provide
    -0.07
    Marshall
    -0.07
    Provision
    -0.07
     Burlington
    -0.07
    اقة
    -0.07
     Provision
    -0.07
     spiral
    -0.07
    φάλ
    -0.07
    POSITIVE LOGITS
    红包
    0.09
    rede
    0.08
     timest
    0.08
    redno
    0.08
     vermeld
    0.08
     тв
    0.07
    IRON
    0.07
    소드
    0.07
     ringtone
    0.07
     �
    0.07
    Activations Density 0.000%

    No Known Activations