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. 58106
    Prev
    Next
    INDEX
    Explanations

    -backed

    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
     massage
    -0.08
     meat
    -0.08
    être
    -0.08
    批
    -0.08
    onya
    -0.07
     defens
    -0.07
     vegan
    -0.07
     değerlend
    -0.07
    OBJ
    -0.07
     OBS
    -0.07
    POSITIVE LOGITS
     EEPROM
    0.14
     SRAM
    0.12
     capacitor
    0.12
     CMOS
    0.11
    (clk
    0.11
    _clk
    0.11
    -memory
    0.10
     BIOS
    0.10
     battery
    0.10
     motherboard
    0.10
    Activations Density 0.004%

    No Known Activations